Comments (5)
Hey
Interesting. Last time I tried running it I had no problem converging and managed to train within a day or two on Titan/Titan Black GPUs.
The UCF-101 patches I uploaded specifically here (the one used in the paper was much larger) is a very small dataset due to memory constraints so as far as I remember I managed to heavily overfit at training set.
I will try finding weights but I can't promise anything :)
from unsupervised-videos.
Thank you for your fast answer!
I just realized I was not that precise.
Up to now I only tried to train it on MovingMNIST. For training data (which is using the ground truth as input to the future-predictor), it is actually converging quite good. I think it was down to a training-loss to about 170, but the validation-loss (which is using the previously predicted frames as input to the future-predictor) stays at a value of about 2600. In consequece, it can predict the first frame very well, but it does not seem to learn the overall motion that good.
from unsupervised-videos.
Hm, I don't remember having this issue of validation loss being way worse compared to training loss.
from unsupervised-videos.
Hi,
Iām a bit late to the party but it seems that I found the reason why this problem occurred. It was actually caused by the bug fixing that occurred in commit fae11d6. During testing, for each time step the sigmoid was applied to the inputs of the LSTM (which are the outputs of the previous stages). But in the end, the sigmoid was applied again to all outputs. This caused it to be incorrectly applied twice for the outputs at t = 0, ā¦, T-2. My pull request (#26) fixes this problem.
Running the default training mode (1 layer LSTM) on MovingMNIST now gives me a validation cross entropy of around 335 after 120k iterations, which is much more consistent with the values reported in the paper.
from unsupervised-videos.
Thanks for noticing and fixing this bug @jbboin !
from unsupervised-videos.
Related Issues (20)
- CUDAMatException HOT 2
- lstm classifier examples
- CUBLAS error HOT 3
- invalid device function{cm.CUDAMatrix.init_random(42)} cudamat.cudamat.CUDAMatException: CUDA error: no error HOT 10
- Questions regarding some design decisions used to train MovingMNIST in the paper HOT 6
- KeyError: "Unable to open object (Object 'lstm_1_enc:w_dense' doesn't exist)"
- Data format HOT 1
- no eps decay? HOT 1
- 1 input -> next predicted output
- Questions about LSTM_classifier HOT 1
- no kernel image is available for execution on the device HOT 2
- runtest failed:[runtest] segmentation fault (core dumped)
- Error while giving the command for training HOT 6
- Extrpolating matrices
- Training with new dataset HOT 1
- Make the file Makefile in the folder cudamat HOT 2
- Request for the script to generate moving mnist video dataset HOT 1
- Videos
- -![image](https://user-images.githubusercontent.com/101527858/159179877-0df83b60-09df-4a31-834b-d59002aba969.jpeg)
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
š Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. ššš
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ā¤ļø Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from unsupervised-videos.